Centre de documentation
scientifique

Early detection of pine wilt disease using deep learning algorithms and UAV-based multispectral imagery / Run Yu in Forest ecology and management, vol 497 (October-1 2021)  

Public [article]  inForest ecology and management > vol 497 (October-1 2021) . - n° 119493 Titre : Early detection of pine wilt disease using deep learning algorithms and UAV-based multispectral imagery Type de document : Article/Communication Auteurs : Run Yu, Auteur ; Youqing Luo, Auteur ; Quan Zhou, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 119493 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage profond [Termes IGN] Chine [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] dépérissement [Termes IGN] image captée par drone [Termes IGN] image multibande [Termes IGN] maladie phytosanitaire [Termes IGN] milieu tropical [Termes IGN] peuplement mélangé [Termes IGN] Pinus (genre) [Termes IGN] Pinus massoniana [Termes IGN] réflectance spectrale [Termes IGN] Ulmus (genre) Résumé : (auteur) Pine wilt disease (PWD) is a global devastating threat to forest ecosystems. Therefore, a feasible and effective approach to precisely monitor PWD infection is indispensable, especially at the early stages. However, a precise definition of “early stage” and a rapid and high-efficiency method to detect PWD infection have not been well established. In this study, we systematically divided the PWD infection into green, early, middle, and late stages based on the needle color, the resin secretion, and whether the pine wood nematode (PWN) was carried. Simultaneously, an unmanned aerial vehicle (UAV) equipped with multispectral cameras was used to obtain images. Two target detection algorithms (Faster R-CNN and YOLOv4) and two traditional machine learning algorithms based on feature extraction (random forest and support vector machine) were employed to realize the recognition of infected pine trees. Moreover, we took into consideration of the influence of green broad-leaved trees on the identification of pine trees at the early stage of PWD infection. We obtained the following results: (1) the accuracy of Faster R-CNN (60.98–66.7%) was higher than that of YOLOv4 (57.07–63.55%), but YOLOv4 outperformed in terms of model size, processing speed, training time, and testing time; (2) although the traditional machine learning models had higher accuracy (73.28–79.64%), they were not able to directly identify the object from the images; (3) the accuracy of early detection of PWD infection showed an increase of 3.72–4.29%, from 42.36–44.59% to 46.08–48.88%, when broad-leaved trees were considered. In this study, the combination of UAV-based multispectral images and target detection algorithms allowed us to monitor the occurrence of PWD and obtain the distribution of infected trees at an early stage, which can provide technical support for the prevention and control of PWD. Numéro de notice : A2021-658 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.foreco.2021.119493 En ligne : https://doi.org/10.1016/j.foreco.2021.119493 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98395 [article]

Applications of remote sensing data in mapping of forest growing stock and biomass / Jose Aranha (2021)  

Public Titre : Applications of remote sensing data in mapping of forest growing stock and biomass Type de document : Monographie Auteurs : Jose Aranha, Éditeur scientifique Editeur : Bâle [Suisse] : Multidisciplinary Digital Publishing Institute MDPI Année de publication : 2021 Importance : 276 p. Format : 16 x 24 cm ISBN/ISSN/EAN : 978-3-0365-0569-5 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage automatique [Termes IGN] biomasse aérienne [Termes IGN] capital sur pied [Termes IGN] carte forestière [Termes IGN] Chine [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] données lidar [Termes IGN] foresterie [Termes IGN] forêt boréale [Termes IGN] image captée par drone [Termes IGN] image Landsat-OLI [Termes IGN] image radar moirée [Termes IGN] image Sentinel-MSI [Termes IGN] image SPOT 6 [Termes IGN] inventaire forestier étranger (données) [Termes IGN] Pinus massoniana [Termes IGN] puits de carbone [Termes IGN] service écosystémique [Termes IGN] système d'information géographique [Termes IGN] Thaïlande Résumé : (éditeur) This Special Issue (SI), entitled "Applications of Remote Sensing Data in Mapping of Forest Growing Stock and Biomass”, resulted from 13 peer-reviewed papers dedicated to Forestry and Biomass mapping, characterization and accounting. The papers' authors presented improvements in Remote Sensing processing techniques on satellite images, drone-acquired images and LiDAR images, both aerial and terrestrial. Regarding the images’ classification models, all authors presented supervised methods, such as Random Forest, complemented by GIS routines and biophysical variables measured on the field, which were properly georeferenced. The achieved results enable the statement that remote imagery could be successfully used as a data source for regression analysis and formulation and, in this way, used in forestry actions such as canopy structure analysis and mapping, or to estimate biomass. This collection of papers, presented in the form of a book, brings together 13 articles covering various forest issues and issues in forest biomass calculation, constituting an important work manual for those who use mixed GIS and RS techniques. Note de contenu : 1- Finer resolution estimation and mapping of mangrove biomass using UAV LiDAR and WorldView-2 data 2- Nondestructive estimation of the above-ground biomass of multiple tree species in boreal forests of China using Terrestrial Laser Scanning 3- Estimating forest aboveground carbon storage in Hang-Jia-Hu using Landsat TM/OLI data and random morest Model 4- Influence of variable selection and forest type on forest aboveground biomass estimation using machine learning algorithms 5- Comparative analysis of seasonal Landsat 8 images for forest aboveground biomass estimation in a subtropical forest 6- Estimating urban vegetation biomass from Sentinel-2A image data 7- Estimation of forest biomass in Beijing (China) using multisource remote sensing and forest inventory data 8- Spatially explicit analysis of trade-offs and synergies among multiple ecosystem services in Shaanxi Valley basin 9- Influence of site-specific conditions on estimation of forest above ground biomass from airborne laser scanning 10- Multi-sensor prediction of stand volume by a hybrid model of support vector machine for regression kriging 11- Applying LiDAR to quantify the plant area index along a successional gradient in a tropical forest of Thailand 12- Shrub biomass estimates in former burnt areas using Sentinel 2 images processing and classification 13- Evaluation of different algorithms for estimating the growing stock volume of pinus massoniana plantations using spectral and spatial information from a SPOT6 image Numéro de notice : 15305 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Recueil / ouvrage collectif DOI : 10.3390/books978-3-0365-0569-5 En ligne : https://doi.org/10.3390/books978-3-0365-0569-5 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99903

Remote sensing technology applications in forestry and REDD+ / Kim Calders (2020)  

Public Titre : Remote sensing technology applications in forestry and REDD+ Type de document : Monographie Auteurs : Kim Calders, Éditeur scientifique ; Inge Jonckheere, Éditeur scientifique ; Mikko Vastaranta, Éditeur scientifique ; Joanne Nightingale, Éditeur scientifique Editeur : Bâle [Suisse] : Multidisciplinary Digital Publishing Institute MDPI Année de publication : 2020 Importance : 244 p. ISBN/ISSN/EAN : 978-3-03928-471-9 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage automatique [Termes IGN] biomasse aérienne [Termes IGN] canopée [Termes IGN] cartographie des risques [Termes IGN] déboisement [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] image Landsat [Termes IGN] image multibande [Termes IGN] image Sentinel [Termes IGN] Pinus massoniana [Termes IGN] polarimétrie radar [Termes IGN] Réduction des émissions dues à la déforestation et la dégradation des forêts, REDD [Termes IGN] télémétrie laser aéroporté [Termes IGN] télémétrie laser terrestre Résumé : (Editeur) Advances in close-range and remote sensing technologies are driving innovations in forest resource assessments and monitoring on varying scales. Data acquired with airborne and spaceborne platforms provide high(er) spatial resolution, more frequent coverage, and more spectral information. Recent developments in ground-based sensors have advanced 3D measurements, low-cost permanent systems, and community-based monitoring of forests. The UNFCCC REDD+ mechanism has advanced the remote sensing community and the development of forest geospatial products that can be used by countries for the international reporting and national forest monitoring. However, an urgent need remains to better understand the options and limitations of remote and close-range sensing techniques in the field of forest degradation and forest change. Therefore, we invite scientists working on remote sensing technologies, close-range sensing, and field data to contribute to this Special Issue. Topics of interest include: (1) novel remote sensing applications that can meet the needs of forest resource information and REDD+ MRV, (2) case studies of applying remote sensing data for REDD+ MRV, (3) timeseries algorithms and methodologies for forest resource assessment on different spatial scales varying from the tree to the national level, and (4) novel close-range sensing applications that can support sustainable forestry and REDD+ MRV. We particularly welcome submissions on data fusion. Numéro de notice : 26296 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Monographie DOI : 10.3390/books978-3-03928-471-9 Date de publication en ligne : 07/04/2020 En ligne : https://doi.org/10.3390/books978-3-03928-471-9 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95009

Mapping spatial distribution of forest age in China / Yuan Zhang in Earth and space science, vol 4 n° 3 (March 2017)  

Public [article]  inEarth and space science > vol 4 n° 3 (March 2017) . - pp 108 - 116 Titre : Mapping spatial distribution of forest age in China Type de document : Article/Communication Auteurs : Yuan Zhang, Auteur ; Yitong Yao, Auteur ; Xuhui Wang, Auteur ; Yongwen Liu, Auteur ; Shilong Piao, Auteur Année de publication : 2017 Article en page(s) : pp 108 - 116 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Végétation [Termes IGN] carte forestière [Termes IGN] Chine [Termes IGN] Cupressaceae [Termes IGN] distribution spatiale [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] forêt ancienne [Termes IGN] hauteur des arbres [Termes IGN] incertitude des données [Termes IGN] inventaire forestier (techniques et méthodes) [Termes IGN] inventaire forestier étranger (données) [Termes IGN] peuplement forestier [Termes IGN] Pinophyta [Termes IGN] Pinus massoniana [Termes IGN] puits de carbone Résumé : (auteur) Forest stand age is a meaningful metric, which reflects the past disturbance legacy, provides guidelines for forest management practices, and is an important factor in qualifying forest carbon cycles and carbon sequestration potential. Reliable large-scale forest stand age information with high spatial resolutions, however, is difficult to obtain. In this study, we developed a top-down method to downscale the provincial statistics of national forest inventory data into 1 km stand age map using climate data and light detection and ranging-derived forest height. We find that the distribution of forest stand age in China is highly heterogeneous across the country, with a mean value of ~42.6 years old. The relatively young stand age for Chinese forests is mostly due to the large proportion of newly planted forests (0–40 years old), which are more prevailing in south China. Older forests (stand age > 60 years old) are more frequently found in east Qinghai-Tibetan Plateau and the central mountain areas of west and northeast China, where human activities are less intensive. Among the 15 forest types, forests dominated by species of , with the exception of Cunninghamia lanceolata stands, have the oldest mean stand age (136 years), whereas Pinus massoniana forests are the youngest (18 years). We further identified uncertainties associated with our forest age map, which are high in west and northeast China. Our work documents the distribution of forest stand age in China at a high resolution which is useful for carbon cycle modeling and the sustainable use of China's forest resources. Numéro de notice : A2107-277 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.1002/2016EA000177 En ligne : https://doi.org/10.1002/2016EA000177 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85298 [article]